Instructions to use marcosremar2/qwen3-1.7b-binary-rp-b3-hold-r64 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use marcosremar2/qwen3-1.7b-binary-rp-b3-hold-r64 with Transformers:

# Use a pipeline as a high-level helper
from transformers import pipeline

pipe = pipeline("text-generation", model="marcosremar2/qwen3-1.7b-binary-rp-b3-hold-r64")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoModel
model = AutoModel.from_pretrained("marcosremar2/qwen3-1.7b-binary-rp-b3-hold-r64", device_map="auto")

Notebooks
Google Colab
Kaggle
Local Apps Settings

llama.cpp

How to use marcosremar2/qwen3-1.7b-binary-rp-b3-hold-r64 with llama.cpp:

Install (macOS, Linux)

curl -LsSf https://llama.app/install.sh | sh
# Start a local OpenAI-compatible server with a web UI:
llama serve -hf marcosremar2/qwen3-1.7b-binary-rp-b3-hold-r64:Q8_0
# Run inference directly in the terminal:
llama cli -hf marcosremar2/qwen3-1.7b-binary-rp-b3-hold-r64:Q8_0

Install from WinGet (Windows)

winget install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama serve -hf marcosremar2/qwen3-1.7b-binary-rp-b3-hold-r64:Q8_0
# Run inference directly in the terminal:
llama cli -hf marcosremar2/qwen3-1.7b-binary-rp-b3-hold-r64:Q8_0

Use pre-built binary

# Download pre-built binary from:
# https://github.com/ggerganov/llama.cpp/releases
# Start a local OpenAI-compatible server with a web UI:
./llama-server -hf marcosremar2/qwen3-1.7b-binary-rp-b3-hold-r64:Q8_0
# Run inference directly in the terminal:
./llama-cli -hf marcosremar2/qwen3-1.7b-binary-rp-b3-hold-r64:Q8_0

Build from source code

git clone https://github.com/ggerganov/llama.cpp.git
cd llama.cpp
cmake -B build
cmake --build build -j --target llama-server llama-cli
# Start a local OpenAI-compatible server with a web UI:
./build/bin/llama-server -hf marcosremar2/qwen3-1.7b-binary-rp-b3-hold-r64:Q8_0
# Run inference directly in the terminal:
./build/bin/llama-cli -hf marcosremar2/qwen3-1.7b-binary-rp-b3-hold-r64:Q8_0

Use Docker

docker model run hf.co/marcosremar2/qwen3-1.7b-binary-rp-b3-hold-r64:Q8_0

LM Studio
Jan

vLLM

How to use marcosremar2/qwen3-1.7b-binary-rp-b3-hold-r64 with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "marcosremar2/qwen3-1.7b-binary-rp-b3-hold-r64"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "marcosremar2/qwen3-1.7b-binary-rp-b3-hold-r64",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/marcosremar2/qwen3-1.7b-binary-rp-b3-hold-r64:Q8_0

SGLang

How to use marcosremar2/qwen3-1.7b-binary-rp-b3-hold-r64 with SGLang:

Install from pip and serve model

# Install SGLang from pip:
pip install sglang
# Start the SGLang server:
python3 -m sglang.launch_server \
    --model-path "marcosremar2/qwen3-1.7b-binary-rp-b3-hold-r64" \
    --host 0.0.0.0 \
    --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "marcosremar2/qwen3-1.7b-binary-rp-b3-hold-r64",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker images

docker run --gpus all \
    --shm-size 32g \
    -p 30000:30000 \
    -v ~/.cache/huggingface:/root/.cache/huggingface \
    --env "HF_TOKEN=<secret>" \
    --ipc=host \
    lmsysorg/sglang:latest \
    python3 -m sglang.launch_server \
        --model-path "marcosremar2/qwen3-1.7b-binary-rp-b3-hold-r64" \
        --host 0.0.0.0 \
        --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "marcosremar2/qwen3-1.7b-binary-rp-b3-hold-r64",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Ollama
How to use marcosremar2/qwen3-1.7b-binary-rp-b3-hold-r64 with Ollama:
```
ollama run hf.co/marcosremar2/qwen3-1.7b-binary-rp-b3-hold-r64:Q8_0
```
Unsloth Desktop

How to use marcosremar2/qwen3-1.7b-binary-rp-b3-hold-r64 with Pi:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf marcosremar2/qwen3-1.7b-binary-rp-b3-hold-r64:Q8_0

Configure the model in Pi

# Install Pi:
npm install -g @earendil-works/pi-coding-agent
# Add to ~/.pi/agent/models.json:
{
  "providers": {
    "llama-cpp": {
      "baseUrl": "http://localhost:8080/v1",
      "api": "openai-completions",
      "apiKey": "none",
      "models": [
        {
          "id": "marcosremar2/qwen3-1.7b-binary-rp-b3-hold-r64:Q8_0"
        }
      ]
    }
  }
}

Run Pi

# Start Pi in your project directory:
pi

Docker Model Runner
How to use marcosremar2/qwen3-1.7b-binary-rp-b3-hold-r64 with Docker Model Runner:
```
docker model run hf.co/marcosremar2/qwen3-1.7b-binary-rp-b3-hold-r64:Q8_0
```

Lemonade

How to use marcosremar2/qwen3-1.7b-binary-rp-b3-hold-r64 with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull marcosremar2/qwen3-1.7b-binary-rp-b3-hold-r64:Q8_0

Run and chat with the model

lemonade run user.qwen3-1.7b-binary-rp-b3-hold-r64-Q8_0

List all available models

lemonade list

Hermes Agent

How to use marcosremar2/qwen3-1.7b-binary-rp-b3-hold-r64 with Hermes Agent:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf marcosremar2/qwen3-1.7b-binary-rp-b3-hold-r64:Q8_0

Configure Hermes

# Install Hermes:
curl -fsSL https://hermes-agent.nousresearch.com/install.sh | bash
hermes setup
# Point Hermes at the local server:
hermes config set model.provider custom
hermes config set model.base_url http://127.0.0.1:8080/v1
hermes config set model.default marcosremar2/qwen3-1.7b-binary-rp-b3-hold-r64:Q8_0

Run Hermes

hermes

Atomic Chat

OpenClaw

How to use marcosremar2/qwen3-1.7b-binary-rp-b3-hold-r64 with OpenClaw:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf marcosremar2/qwen3-1.7b-binary-rp-b3-hold-r64:Q8_0

Configure OpenClaw

# Install OpenClaw:
npm install -g openclaw@latest
# Register the local server and set it as the default model:
openclaw onboard --non-interactive --mode local \
  --auth-choice custom-api-key \
  --custom-base-url http://127.0.0.1:8080/v1 \
  --custom-model-id "marcosremar2/qwen3-1.7b-binary-rp-b3-hold-r64:Q8_0" \
  --custom-provider-id llama-cpp \
  --custom-compatibility openai \
  --custom-text-input \
  --accept-risk \
  --skip-health

Run OpenClaw

openclaw agent --local --agent main --message "Hello from Hugging Face"

b3_binary_hold_r64 — Qwen3-1.7B LoRA-QAT binary (roleplay PT-BR)

Manual LoRA + binary QAT adapter for Qwen3-1.7B, trained for Brazilian Portuguese roleplay.

Results (vs Bonsai 1.7B baseline ~82.5)

Metric	Value
Aggregate RP (3 seeds)	89.27 ± 2.06
PT purity	1.000
ACCatom	1.000
Collapsed	0
blend_alpha (train ckpt / bench)	1.0 / 1.0

Seeds: 42 → 91.2 · 123 → 89.5 · 2026 → 87.1
Eval: data/pt_rp_v3_test (42 scenes), script bench_v8_lora.py.

Training recipe

Base: Qwen3-1.7B
Quant: binary on MLP only (quant_targets=mlp)
Schedule: warmup 300 → ramp 1200 → full α=1.0 from step 1500; saved at step 6600
LoRA: r=64, alpha=128, residual=True, rsLoRA, soft-tanh STE, pre-RMSNorm
KD: KL weight 2.0, temp 5.0
Data: cpt_mix_v3/train.jsonl
Early-stop: smoke_5fail@6700 (full eval still strong)

Files

File	Description
`best_lora.pt`	Best checkpoint (by val loss) — use this
`final_lora.pt`	Last step before smoke abort
`adapter_config.json`	Hyperparameters for loading
`exp_metrics.json`	Training metrics
`bench_results.json`	Full 3-seed eval

Load (cluster / repo scripts)

import torch
from scripts.exp_v8_lora import inject_lora, load_v8_lora, set_quant_schedule
from scripts.bench_v8_lora import ...  # or train helpers

ckpt = torch.load("best_lora.pt", map_location="cpu", weights_only=False)
# inject_lora(..., quant_mode="binary", r=64, alpha=128, residual=True,
#             quant_targets="mlp", use_rmsnorm=True, rs_lora=True, soft_tanh=True)
# set_quant_schedule(warmup+ramp, warmup, ramp)  # force alpha=1.0
# load_v8_lora(model, "best_lora.pt")

Not a PEFT/peft adapter — custom LoRALinear + binary STE from this project.

License

Weights are a derivative of Qwen3-1.7B. Follow the base model license (Apache 2.0) and applicable Qwen terms.

Downloads last month: 19

GGUF

Model size

2B params

Architecture

qwen3

Hardware compatibility

8-bit

Model tree for marcosremar2/qwen3-1.7b-binary-rp-b3-hold-r64

Base model

Qwen/Qwen3-1.7B-Base

Finetuned

Qwen/Qwen3-1.7B

Adapter

(649)

this model